Pith. sign in

Physics of language models: Part 3.3, knowledge capacity scaling laws

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

A Lightweight Method to Disrupt Memorized Sequences in LLM

cs.LG · 2025-02-07 · conditional · novelty 6.0

A decoding-time intervention that substitutes a small model's probabilities for common function words into a large model's output reduces exact training-data recall by up to 10x with minimal measured quality loss.

citing papers explorer

Showing 1 of 1 citing paper.

  • A Lightweight Method to Disrupt Memorized Sequences in LLM cs.LG · 2025-02-07 · conditional · none · ref 5

    A decoding-time intervention that substitutes a small model's probabilities for common function words into a large model's output reduces exact training-data recall by up to 10x with minimal measured quality loss.